diff --git a/server/text_generation_server/models/bloom.py b/server/text_generation_server/models/bloom.py
index 65c9f317..156b660f 100644
--- a/server/text_generation_server/models/bloom.py
+++ b/server/text_generation_server/models/bloom.py
@@ -90,6 +90,7 @@ class BLOOMSharded(CausalLM):
 
         torch.distributed.barrier(group=self.process_group)
         super(CausalLM, self).__init__(
+            model_id=model_id,
             model=model,
             tokenizer=tokenizer,
             requires_padding=True,
diff --git a/server/text_generation_server/models/causal_lm.py b/server/text_generation_server/models/causal_lm.py
index e896c831..10c64c66 100644
--- a/server/text_generation_server/models/causal_lm.py
+++ b/server/text_generation_server/models/causal_lm.py
@@ -538,6 +538,7 @@ class CausalLM(Model):
                 tokenizer.add_special_tokens({"pad_token": "[PAD]"})
 
         super(CausalLM, self).__init__(
+            model_id=model_id,
             model=model,
             tokenizer=tokenizer,
             requires_padding=True,
diff --git a/server/text_generation_server/models/galactica.py b/server/text_generation_server/models/galactica.py
index d0f2b915..e74d2cbf 100644
--- a/server/text_generation_server/models/galactica.py
+++ b/server/text_generation_server/models/galactica.py
@@ -212,6 +212,7 @@ class GalacticaSharded(CausalLM):
 
         torch.distributed.barrier(group=self.process_group)
         super(CausalLM, self).__init__(
+            model_id=model_id,
             model=model,
             tokenizer=tokenizer,
             requires_padding=True,
diff --git a/server/text_generation_server/models/gpt_neox.py b/server/text_generation_server/models/gpt_neox.py
index c0e1adf2..0131bffc 100644
--- a/server/text_generation_server/models/gpt_neox.py
+++ b/server/text_generation_server/models/gpt_neox.py
@@ -65,6 +65,7 @@ class GPTNeoxSharded(CausalLM):
 
         torch.distributed.barrier(group=self.process_group)
         super(CausalLM, self).__init__(
+            model_id=model_id,
             model=model,
             tokenizer=tokenizer,
             requires_padding=True,
diff --git a/server/text_generation_server/models/mpt.py b/server/text_generation_server/models/mpt.py
index 8d8b4909..c58b387e 100644
--- a/server/text_generation_server/models/mpt.py
+++ b/server/text_generation_server/models/mpt.py
@@ -90,6 +90,7 @@ class MPTSharded(CausalLM):
 
         torch.distributed.barrier(group=self.process_group)
         super(CausalLM, self).__init__(
+            model_id=model_id,
             model=model,
             tokenizer=tokenizer,
             requires_padding=False,
diff --git a/server/text_generation_server/models/opt.py b/server/text_generation_server/models/opt.py
index 5b84f4ff..aaf81f21 100644
--- a/server/text_generation_server/models/opt.py
+++ b/server/text_generation_server/models/opt.py
@@ -63,6 +63,7 @@ class OPTSharded(CausalLM):
 
         torch.distributed.barrier(group=self.process_group)
         super(CausalLM, self).__init__(
+            model_id=model_id,
             model=model,
             tokenizer=tokenizer,
             requires_padding=True,
diff --git a/server/text_generation_server/models/phi.py b/server/text_generation_server/models/phi.py
index d68866c1..93d42b2b 100644
--- a/server/text_generation_server/models/phi.py
+++ b/server/text_generation_server/models/phi.py
@@ -60,6 +60,7 @@ class Phi(CausalLM):
         model = PhiForCausalLM(config, weights)
         torch.distributed.barrier(group=self.process_group)
         super(CausalLM, self).__init__(
+            model_id=model_id,
             model=model,
             tokenizer=tokenizer,
             requires_padding=True,
diff --git a/server/text_generation_server/models/rw.py b/server/text_generation_server/models/rw.py
index d4764ded..bc2b6db2 100644
--- a/server/text_generation_server/models/rw.py
+++ b/server/text_generation_server/models/rw.py
@@ -62,6 +62,7 @@ class RW(CausalLM):
                 tokenizer.add_special_tokens({"pad_token": "[PAD]"})
 
         super(CausalLM, self).__init__(
+            model_id=model_id,
             model=model,
             tokenizer=tokenizer,
             requires_padding=True,
diff --git a/server/text_generation_server/models/santacoder.py b/server/text_generation_server/models/santacoder.py
index 323e4324..caddbe19 100644
--- a/server/text_generation_server/models/santacoder.py
+++ b/server/text_generation_server/models/santacoder.py
@@ -62,6 +62,7 @@ class SantaCoder(CausalLM):
             )
 
         super(CausalLM, self).__init__(
+            model_id=model_id,
             model=model,
             tokenizer=tokenizer,
             requires_padding=True,
diff --git a/server/text_generation_server/models/seq2seq_lm.py b/server/text_generation_server/models/seq2seq_lm.py
index 3bd09556..d454d804 100644
--- a/server/text_generation_server/models/seq2seq_lm.py
+++ b/server/text_generation_server/models/seq2seq_lm.py
@@ -575,6 +575,7 @@ class Seq2SeqLM(Model):
         tokenizer.bos_token_id = model.config.decoder_start_token_id
 
         super(Seq2SeqLM, self).__init__(
+            model_id=model_id,
             model=model,
             tokenizer=tokenizer,
             requires_padding=True,
diff --git a/server/text_generation_server/models/t5.py b/server/text_generation_server/models/t5.py
index 8e0735e5..adef664c 100644
--- a/server/text_generation_server/models/t5.py
+++ b/server/text_generation_server/models/t5.py
@@ -73,6 +73,7 @@ class T5Sharded(Seq2SeqLM):
 
         torch.distributed.barrier(group=self.process_group)
         super(Seq2SeqLM, self).__init__(
+            model_id=model_id,
             model=model,
             tokenizer=tokenizer,
             requires_padding=True,